Jupyter python kernel dies - OpenAI

Question

I am new to reinforcement learning and I am trying to use OpenAI Gym environments.
First, I installed gym by this command: !pip install gym in jupyter
And after running again to making sure it is installed completely, I got this output:

Requirement already satisfied: gym in c:\program files\anaconda3\lib\site-packages (0.10.5)
Requirement already satisfied: pyglet>=1.2.0 in c:\program files\anaconda3\lib\site-packages (from gym) (1.3.2)
Requirement already satisfied: six in c:\program files\anaconda3\lib\site-packages (from gym) (1.11.0)
Requirement already satisfied: requests>=2.0 in c:\program files\anaconda3\lib\site-packages (from gym) (2.19.1)
Requirement already satisfied: numpy>=1.10.4 in c:\program files\anaconda3\lib\site-packages (from gym) (1.13.3)
Requirement already satisfied: future in c:\program files\anaconda3\lib\site-packages (from pyglet>=1.2.0->gym) (0.16.0)
Requirement already satisfied: urllib3=1.21.1 in c:\program files\anaconda3\lib\site-packages (from requests>=2.0->gym) (1.23)
Requirement already satisfied: certifi>=2017.4.17 in c:\program files\anaconda3\lib\site-packages (from requests>=2.0->gym) (2018.4.16)
Requirement already satisfied: chardet=3.0.2 in c:\program files\anaconda3\lib\site-packages (from requests>=2.0->gym) (3.0.4)
Requirement already satisfied: idna=2.5 in c:\program files\anaconda3\lib\site-packages (from requests>=2.0->gym) (2.7)

As mentioned on OpenAI Gym Doc page, I tried this code to make sure everything is fine:

import gym
env = gym.make('CartPole-v0')
for i_episode in range(20):
    observation = env.reset() #The process gets started by calling reset(), which returns an initial observation. 
    for t in range(100):
        env.render()
        print(observation)
        action = env.action_space.sample()
        observation, reward, done, info = env.step(action)
        if done:
            print("Episode finished after {} timesteps".format(t+1))
            break

After running this code, a new window opens and all things are exactly as provided video on doc page.
But the problem is when agent done (all episodes ran), kernel dies and restart again.

I found in some specific versions, gym.make(close=true) could solve the problem. But not in the latest version of anaconda and Gym. the other solution is using this code: env = gym.make('name') env.close() . but the problem is, this close() function, will delete env object so every time we create envrironment.

Regards

Answer 1

I don't know how to solve this, but I used a different code in gym-retro and it works pretty well.

env = retro.make(game="StreetFighterIISpecialChampionEdition-Genesis", state="ChunLiVsBlanka.1star")
env = wrapper(env)
model = PPO2.load("D:/Python/Projects/Hakisa/rl_model_1000000_steps")
obs = env.reset()
total_reward = []
steps = 0
end = False

while end != True and steps < 100:
    env.render()
    action, state = model.predict(obs)
    obs, reward, end, info = env.step(action)
    steps += 1
    total_reward.append(reward)
    time.sleep(0.05)